We found an easy and quick post-learning method named "Icing on the Cake" to enhance a classification performance in deep learning. The method is that we train only the final classifier again after an ordinary training is done.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “quick learning”
Efficient clustering in high dimensions with Quick Shift and LSH.
problem Density-based clustering in high-dimensional data.
method Combines Quick Shift and LSH for efficient density estimation.
result Achieves almost linear time complexity for consistency.
Quick Shift is a popular mode-seeking and clustering algorithm. We present finite sample statistical consistency guarantees for Quick Shift on mode and cluster recovery under mild distributional assumptions. We then apply our results to construct a consistent modal regression algorithm.
A quick overview is provided on the current development of the WP metric geometry.
Detects data drift in deep learning models using neural embeddings.
problem Detecting changes in data distribution in deep learning models.
method Formulates drift detection in a sequential decision framework and introduces a loss function to balance false alarms and quick detection.
result Demonstrates improved ability to balance false alarms and quick detection in change detection.
Study compares different superpixel methods for explaining CNNs in biological images.
problem Transparency of deep learning models in image classification.
method Compared Felzenszwalb, SLIC, and Compact-Watershed superpixel methods on explaining CNNs.
result Compact-Watershed method most closely matches human-referenced relevance areas.
In this short communication we introduce the quick clustering algorithm (QUIST), an efficient hierarchical clustering algorithm based on sorting. QUIST is a poly-logarithmic divisive clustering algorithm that does not assume the number of clusters, and/or the cluster size to be known ahead of time. It is also insensiti…
Quickly adapts fault diagnosis models for industrial machines.
problem Fault diagnostic models trained for lab machines fail on industrial ones.
method Net2Net transformation followed by fine-tuning.
result Models can be quickly adapted for new operating conditions.
We provide initial seedings to the Quick Shift clustering algorithm, which approximate the locally high-density regions of the data. Such seedings act as more stable and expressive cluster-cores than the singleton modes found by Quick Shift. We establish statistical consistency guarantees for this modification. We then…
Geometric model for Hodge filtered complex cobordism constructed.
problem Constructing a geometric model for Hodge filtered complex cobordism.
method Refinement of Pontryagin-Thom construction to create an explicit isomorphism.
result Explicit isomorphism between geometric and abstract models for complex manifolds.
K-priors enable quick adaptation with minimal retraining.
problem Machine learning models struggle to adapt to changes efficiently.
method Combines weight and function-space priors to reconstruct past gradients.
result Adaptation with K-priors achieves similar performance to full retraining with less data.
This paper gives a quick overview of the author's recent result that all finitely presented groups are QSF.
K-means -- and the celebrated Lloyd algorithm -- is more than the clustering method it was originally designed to be. It has indeed proven pivotal to help increase the speed of many machine learning and data analysis techniques such as indexing, nearest-neighbor search and prediction, data compression; its beneficial u…
A quick review of European financial stability institutions and the role of stress tests in the current juridical system.
A quick proof of Bing's theorem indicated by the title is given. The proof also concludes Gumerov's result on covering degrees of solenoids.
Minimal submanifoldsmath.DG
In what follows we give a quick tour through the field of minimal submanifolds, starting at the definition and the classical results and ending up with current areas of research.
The simulator is an R package that streamlines the process of performing simulations by creating a common infrastructure that can be easily used and reused across projects. Methodological statisticians routinely write simulations to compare their methods to preexisting ones. While developing ideas, there is a temptatio…
The controlled end and h-cobrodism theorems (Ends of maps I, 1979) are used to give quick proofs of the Top/PL and PL/DIFF product structure theorems.
ChatGPT models classify financial texts with minimal training.
problem Few-shot text classification in finance with limited labels.
method In-context learning with GPT-3.5 and GPT-4, fine-tuning with SetFit.
result GPT models outperform fine-tuned models with fewer examples.
One of the classical problems in machine learning and data mining is feature selection. A feature selection algorithm is expected to be quick, and at the same time it should show high performance. MeLiF algorithm effectively solves this problem using ensembles of ranking filters. This article describes two different wa…
This paper proposes new get-rich-quick schemes that involve trading in a financial security with a non-degenerate price path. For simplicity the interest rate is assumed zero. If the price path is assumed continuous, the trader can become infinitely rich immediately after it becomes non-constant (if it ever does). If i…
We present a few general results on foliations of 4-manifolds by surfaces: existence, tautness, relations to minimal genus of embedded surfaces; as well as some open problems. We hope to stimulate interest in this area.
Lectures on Kähler Geometrymath.DG
These notes, based on a graduate course I gave at Hamburg University in 2003, are intended to students having basic knowledges of differential geometry. Their main purpose is to provide a quick and accessible introduction to different aspects of Kähler geometry.
Boosted decision trees enjoy popularity in a variety of applications; however, for large-scale datasets, the cost of training a decision tree in each round can be prohibitively expensive. Inspired by ideas from the multi-arm bandit literature, we develop a highly efficient algorithm for computing exact greedy-optimal d…
Directly proves Wu's theorem on negative curvature metrics.
problem Subadditivity of Hermitian metrics of negative holomorphic sectional curvature.
method Quick direct proof
result Subadditivity of Hermitian metrics of negative holomorphic sectional curvature.
The homology and cohomology of quandles and racks are used in knot theory: given a finite quandle and a cocycle, we can construct a knot invariant. This is a quick introductory survey to the invariants of knots derived from quandles and racks.
In these lecture notes, we give a quick account of the theory of Poisson groupoids and Lie bialgebroids. In particular, we discuss the universal lifting theorem and its applications including integration of quasi-Lie bialgebroids, integration of Poisson Nijenhuis structures and Alekseev and Kosmann-Schwarzbach's theory…
If the group of a 2-knot group has an abelian normal subgroup of rank which is not finitely generated then either has no minimal Seifert hypersurface or is topologically equivalent to Example 10 of Ralph Fox's``{\it A quick trip through knot theory}".
Recent work on stable minimal hypersurface singularities.
problem Understanding singularities of stable minimal hypersurfaces.
method Simplifications of technical discussion in previous work.
result Simplified approach to analyzing hypersurface singularities.
The high structural deficient rate poses serious risks to the operation of many bridges and buildings. To prevent critical damage and structural collapse, a quick structural health diagnosis tool is needed during normal operation or immediately after extreme events. In structural health monitoring (SHM), many existing …
We prove that the twisted Reidemeister torsion of a 3-manifold corresponding to a fibered class is monic and we show that it gives lower bounds on the Thurston norm. The former fixes a flawed proof in [FV10], the latter gives a quick alternative argument for the main theorem of [FK06].
In this chapter, we provide a brief overview of applying machine learning techniques for clinical prediction tasks. We begin with a quick introduction to the concepts of machine learning and outline some of the most common machine learning algorithms. Next, we demonstrate how to apply the algorithms with appropriate to…
There is a relation between the generalized Property R Conjecture and the Schoenflies Conjecture that suggests a new line of attack on the latter. The approach gives a quick proof of the genus 2 Schoenflies Conjecture and suffices to prove the genus 3 case, even in the absence of new progress on the generalized Propert…
This paper has two purposes. First it partially extends the result in the author's previous work concerning the asymptotic expansion of the Tian-Yau metrics, by considering a slightly larger class of quasi-projective manifolds. This text is also intended to provide a quick introductory reference to the study of Ricci-f…
Powershap speeds up feature selection for machine learning models.
problem Feature selection in machine learning models is crucial but computationally expensive.
method Powershap combines statistical hypothesis testing and Shapley values for quick feature selection.
result Powershap outperforms other methods with similar predictive performance and significantly faster execution.
This paper introduces quantum invariants for 3-alterfolds and proves their consistency with topological moves.
problem Quantum invariants for 3-alterfolds and their consistency with topological moves.
method Introduction of 3-alterfolds with embedded separating surfaces and spherical fusion categories.
result Quantum invariants of 3-alterfolds are consistent with topological moves and generalize invariants of 3-manifolds containing framed links.
In this note we examine a natural concept of a curve on a supermanifold and the subsequent notion of the jet of a curve. We then tackle the question of geometrically defining the higher order tangent bundles of a supermanifold. Finally we make a quick comparison with the notion of a curve presented here are other commo…
Surveying deep meta-learning to improve quick concept learning.
problem Limitation of deep neural networks in learning new concepts quickly.
method Categorizes deep meta-learning techniques into metric, model, and optimization-based approaches.
result Unified overview of current deep meta-learning techniques.
Provides an overview of Bartnik's quasi-local mass.
problem Understanding Bartnik's quasi-local mass.
method Surveys results on Bartnik's quasi-local mass.
result Serves as an entry point and quick reference.
We give a quick tour through many of the classical results in the field of minimal submanifolds, starting at the definition. The field of minimal submanifolds remains extremely active and has very recently seen major developments that have solved many longstanding open problems and conjectures; for more on this, see th…
We present SEALion: an extensible framework for privacy-preserving machine learning with homomorphic encryption. It allows one to learn deep neural networks that can be seamlessly utilized for prediction on encrypted data. The framework consists of two layers: the first is built upon TensorFlow and SEAL and exposes sta…
Handling previously unseen tasks after given only a few training examples continues to be a tough challenge in machine learning. We propose TapNets, neural networks augmented with task-adaptive projection for improved few-shot learning. Here, employing a meta-learning strategy with episode-based training, a network and…
This work proposes external correctors for quick AI error corrections without system modification.
problem Quick corrections of AI errors without modifying legacy systems.
method Special `external` devices with classifiers for high-dimensional data.
result Simple classifiers can correct small errors in high-dimensional data.
New method identifies distribution grid outages using smart meter data.
problem Outages in urban distribution grids due to DERs and smart meters' last gasp signals.
method Data-driven approach based on stochastic time series analysis and maximum likelihood estimation.
result Proves optimal performance in identifying distribution grid outages using smart meter data.
In a classic paper Zeeman introduced the k-twist spin of a knot K and showed that the exterior of a twist spin fibers over S^1. In particular this result shows that the knot K # -K is doubly slice. In this paper we give a quick proof of Zeeman's result. The k-twist spin of K also gives rise to two metabolizers for K # …
Revisiting Classical Bagging with Modern Transfer Learning for On-the-fly Disaster Damage Detectorcs.LG
Paper improves disaster damage detection using modern transfer learning.
problem Harder to obtain damaged examples than undamaged ones.
method Revisits classical bagging with modern transfer learning.
result Significantly outperforms existing methodologies.
We show that in any -Gorenstein flat family of klt singularities, normalized volumes are lower semicontinuous with respect to the Zariski topology. A quick consequence is that smooth points have the largest normalized volume among all klt singularities. Using an alternative characterization of K-semistabili…
We give results on when a finitely generated group has only indiscrete embeddings in SL(2,C), with particular reference to 3-manifold groups. For instance if we glue two copies of the figure 8 knot along its torus boundary then the fundamental group of the resulting closed 3-manifold sometimes embeds in SL(2,C) and som…